CN111724783A

CN111724783A - Awakening method and device of intelligent equipment, intelligent equipment and medium

Info

Publication number: CN111724783A
Application number: CN202010589348.4A
Authority: CN
Inventors: 史润宇; 张琳; 华雨晴; 美耸; 路炜; 郭奶超; 王凯
Original assignee: Beijing Xiaomi Mobile Software Co Ltd
Current assignee: Beijing Xiaomi Mobile Software Co Ltd
Priority date: 2020-06-24
Filing date: 2020-06-24
Publication date: 2020-09-29
Anticipated expiration: 2040-06-24
Also published as: CN111724783B; US20210410065A1; EP3929723A1

Abstract

The disclosure relates to a method and a device for waking up an intelligent device, the intelligent device and a medium, wherein the waking up method comprises the following steps: receiving sound information; judging whether the sound information contains multi-frequency sound; and if the sound information contains multi-frequency sound, awakening the preset function of the intelligent equipment. The awakening method in the disclosure judges whether the sound information received by the intelligent device contains multi-frequency sound so as to determine whether to awaken the preset function of the intelligent device. Because this disclosure uses the frequency domain characteristic as the basis of judging, when guaranteeing to awaken up the accuracy, can also reduce the complexity in the sound information processing process, reduce the energy consumption of smart machine.

Description

Awakening method and device of intelligent equipment, intelligent equipment and medium

Technical Field

The present disclosure relates to the field of intelligent devices, and in particular, to a method and an apparatus for waking up an intelligent device, and a medium.

Background

With the progress of the technology, the wake-up technology is more and more widely applied. With the increasing abundance of scenes in which a system needs to be awakened, in order to enable various systems to be awakened in appropriate scenes, and to ensure that the awakening process is accurate and the low power consumption state is maintained, higher and higher requirements are provided for the awakening technology. The awakening technology matched with the awakening scene can enable the intelligent equipment to be in a standby state for most of time, and awaken when the intelligent equipment needs to be used, so that the power consumption of the intelligent equipment is saved, and meanwhile, the human-computer interaction experience is enhanced.

In the related art, different wake-up techniques are applied to different wake-up scene classifications. For example, the sound control lamp in the corridor wakes up the scheme that the sound control lamp is turned on simply and with low power consumption, but easily causes the mistake to wake up, and the wake-up rate is difficult to master. For another example, a complex artificial intelligence voice wake-up technology, such as a wake-up process of a mobile phone assistant, has a high recognition complexity, requires a complex training process in a test stage, and has a large amount of calculation for the voice recognition process in the wake-up process, thereby increasing the power consumption of the mobile phone.

Disclosure of Invention

To overcome the problems in the related art, the present disclosure provides a method and an apparatus for waking up an intelligent device, and a medium.

According to a first aspect of the embodiments of the present disclosure, a wake-up method for an intelligent device is provided, which is applied to a receiving-end intelligent device, and the wake-up method includes:

receiving sound information;

judging whether the sound information contains multi-frequency sound;

and if the sound information contains multi-frequency sound, awakening the preset function of the intelligent equipment according to the multi-frequency sound.

Optionally, the waking up a preset function of the smart device according to the multi-frequency comprises:

framing the multi-frequency sound;

determining frame energy information for each frame of data of the multi-tone;

determining whether the multi-frequency sound is awakening information according to frame energy information of each frame of data of the multi-frequency sound;

and if the multi-frequency sound is awakening information, awakening the preset function of the intelligent equipment.

Optionally, the determining whether the multi-frequency tone is wake-up information according to frame energy information of each frame of data of the multi-frequency tone includes:

judging whether frame energy information of continuous N frame data exceeds a preset energy threshold value or not;

and if so, determining the multi-frequency tone as the awakening information.

Optionally, the determining whether the sound information includes multi-frequency sound includes:

judging whether the sound information contains characteristic audio information or not according to first preset information;

if the sound information contains characteristic audio information, the sound information contains multi-frequency sound;

wherein the characteristic audio information comprises a plurality of single tones, the first preset information comprises a plurality of reference single tone characteristics, and the plurality of single tones correspond to the plurality of reference single tone characteristics.

determining whether the multi-frequency tone is awakening information according to the energy information of the single-frequency tones;

Optionally, the determining whether the multi-frequency tone is a wake-up message according to the energy information of the single-frequency tones includes:

respectively carrying out frame processing on each single-frequency tone;

respectively determining frame energy information of each frame data of each single-frequency tone;

and determining whether the multi-frequency tone is awakening information according to the frame energy information of each single-frequency tone.

Optionally, the determining whether the multi-frequency tone is a wake-up message according to the frame energy information of each single-frequency tone includes:

respectively judging whether the frame energy information of each single-frequency tone meets a preset condition, wherein the preset condition is that the single-frequency tone has continuous N frames of signals, and the frame energy information of each frame of data exceeds a preset energy threshold corresponding to the single-frequency tone;

and if each single-frequency tone meets a preset condition, determining the multi-frequency tone as wake-up information.

Optionally, the wake-up method further includes:

judging whether the sound information contains characteristic fundamental frequency information or not according to second preset information, wherein the second preset information comprises a reference fundamental frequency characteristic, and the characteristic fundamental frequency information corresponds to the reference fundamental frequency characteristic;

and if the sound information contains characteristic fundamental frequency information, awakening the preset function of the intelligent equipment according to the multi-frequency sound.

Optionally, when the preset function is an ultrasound system function of the smart device, the waking method includes:

and determining the time length of the ultrasonic coding of the ultrasonic system according to the received time length of the multi-frequency sound.

Optionally, the determining, according to the time length of receiving the multitone, the time length of performing ultrasound coding by the ultrasound system includes:

controlling an ultrasonic system to start ultrasonic coding from the moment when the multi-frequency sound is received;

and controlling the ultrasonic system to stop ultrasonic coding from the moment when the multi-frequency sound stops.

According to a second aspect of the embodiments of the present disclosure, there is provided a wake-up apparatus for an intelligent device, which is applied to a receiving-end intelligent device, the wake-up apparatus including:

the radio module is used for receiving sound information;

the processing module is used for judging whether the sound information contains multi-frequency sound;

the processing module is further configured to wake up a preset function of the intelligent device if the sound information includes multi-frequency sound.

Optionally, the processing module is specifically configured to:

framing the multi-frequency sound;

determining frame energy information for each frame of data of the multi-tone;

Optionally, the processing module is specifically configured to:

and if so, determining the multi-frequency tone as the awakening information.

Optionally, the processing module is specifically configured to:

Preferably, the processing module is specifically configured to:

respectively carrying out frame processing on each single-frequency tone;

Optionally, the processing module has a processor for:

Optionally, the processing module is specifically configured to:

Optionally, when the preset function is an ultrasound system function of the smart device, the wake-up module is specifically configured to:

Optionally, the processing module is specifically configured to:

According to a third aspect of the embodiments of the present disclosure, there is provided a smart device, including:

a processor;

a memory for storing executable instructions of the processor;

wherein the processor is configured to perform the wake-up method of the smart device as described above.

According to a fourth aspect of embodiments of the present disclosure, there is provided a non-transitory computer-readable storage medium, wherein instructions, when executed by a processor of a smart device, enable the smart device to perform the wake-up method of the smart device as described above.

The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects: the awakening method in the disclosure judges whether the sound information received by the intelligent device contains multi-frequency sound so as to determine whether to awaken the preset function of the intelligent device. Because this disclosure uses the frequency domain characteristic as the basis of judging, when guaranteeing to awaken up the accuracy, can also reduce the complexity in the sound information processing process, reduce the energy consumption of smart machine.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.

Fig. 1 is a block diagram illustrating a signal transmitting end according to an exemplary embodiment.

Fig. 2 is a block diagram illustrating a transmitting end device and a receiving end device according to an example embodiment.

Fig. 3 is a schematic frequency spectrum diagram illustrating wake-up information containing multi-tones according to an example embodiment.

Fig. 4 is a diagram illustrating a frequency spectrum containing multi-tones and musical fundamental frequencies according to an exemplary embodiment.

Fig. 5 is a flow chart illustrating a wake-up method according to an example embodiment.

Fig. 6 is a flow chart illustrating a wake-up method according to an example embodiment.

Fig. 7 is a flow chart illustrating a wake-up method according to an example embodiment.

Fig. 8 is a flow chart illustrating a wake-up method according to an example embodiment.

Fig. 9 is a flow chart illustrating a wake-up method according to an example embodiment.

Fig. 10 is a block diagram illustrating a signal transmitting end and a receiving end according to an example embodiment.

FIG. 11 is a flow chart illustrating a wake-up method according to an example embodiment.

Fig. 12 is a flow chart illustrating a wake-up method according to an example embodiment.

Fig. 13 is a flow chart illustrating a wake-up method according to an example embodiment.

FIG. 14 is a flow chart illustrating a wake-up method according to an example embodiment.

FIG. 15 is a block diagram illustrating a wake-up unit in accordance with an exemplary embodiment.

FIG. 16 is a block diagram illustrating a smart device according to an example embodiment.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.

Different wake up techniques are applied for different wake up scene categories. For example, the sound control lamp in the corridor wakes up the scheme that the sound control lamp is turned on simply and with low power consumption, but easily causes the mistake to wake up, and the wake-up rate is difficult to master. For another example, a complex artificial intelligence voice wake-up technology, such as a wake-up process of a mobile phone assistant, has a high recognition complexity, requires a complex training process in a test stage, and has a large amount of calculation for the voice recognition process in the wake-up process, thereby increasing the power consumption of the mobile phone.

In the related art, there is a method of waking up a system using a radio frequency technology. For example, the radio frequency identification system in the fields of intelligent transportation, warehouse logistics and the like comprises a radio frequency wake-up circuit transmitting end and a radio frequency wake-up circuit receiving end, the working frequency of the radio frequency wake-up circuit transmitting end is a 915MHZ public frequency band, and the effective wake-up working range is 20 m. And after the active electronic tag enters a working range, awakening a processor of the active RFID electronic tag, and after the processor and the active FRID card reader complete data processing, entering a dormant state again until being awakened next time. However, hardware devices such as radio frequency equipment and radio frequency tags are high in cost, are not suitable for daily life, and are mostly applied to special markets.

The present disclosure provides a method for waking up an intelligent device, wherein when the device receives a sound message, whether the sound message contains multi-frequency sound is determined, and then a preset function is woken up or a current state is maintained. Compared with the voice awakening method in the prior art and the awakening method based on the sound intensity, the awakening method in the disclosure can ensure the awakening accuracy, reduce the complexity in the sound information processing process and reduce the energy consumption of the intelligent device.

The intelligent device may be, for example, a device used as a sound information receiving end, such as a mobile phone, a tablet computer, an intelligent sound box, and an intelligent household appliance. Moreover, the wake-up method in the present disclosure is not limited to the wake-up process of the standby state of the smart device, but may also be applied to the wake-up process of the preset function of the smart device. For example, the ultrasonic module of the mobile phone is awakened to start encoding. For another example, when the temperature and humidity detection device detects that the temperature is lower than the set temperature, the air conditioner is awakened to start to adjust the temperature; and when the detected humidity is lower than the set temperature, waking up the humidifier to start up for humidity adjustment.

The awakening method of the intelligent device is applied to a receiving end intelligent device for receiving awakening information, sample awakening information is stored in the intelligent device in advance, when the intelligent device receives the sound information, whether the sound information contains the sample awakening information or not is determined according to the prestored sample awakening information, and if the sound information contains the sample awakening information, the preset function of the intelligent device is awakened. And if the sound information does not contain the sample awakening information, not awakening the preset function of the intelligent equipment.

In order to wake up the smart device, it is necessary to have another device capable of emitting the wake-up information containing the sample, i.e., the sound information emitting end. In one example, when the temperature and humidity detection device detects that the temperature is lower than the set temperature, the temperature and humidity detection device sends out sound information containing sample awakening information so as to awaken the air conditioner to start for temperature adjustment. In this example, the temperature and humidity detecting device is a transmitting end device of the sound information, and the air conditioner is a receiving end device of the sound information.

In another example, when the temperature and humidity detection device detects that the humidity is lower than the set temperature, the sound information including the sample wake-up information is emitted, and the humidifier is woken up to perform humidity adjustment. At this time, the temperature and humidity detection device serves as a transmitting terminal device for the sample awakening information, and the humidifier serves as a receiving terminal device for receiving the sample awakening information.

Since the multi-frequency is used in the wake-up message of the awakened smart device in the present disclosure, if the smart device on the sound information receiving end is to be awakened, the transmitting end device needs to send out the sound information containing the multi-frequency. Therefore, it is necessary to write multi-tone information in advance into the apparatus for issuing wake-up information, that is, the smart device as the sound information transmitting end has a function of issuing multi-tone.

Since the device for sending the wake-up message needs to send a sound, the smart device can receive the wake-up message. As shown in fig. 1, the apparatus needs to have a multi-tone generator 110, a digital-to-analog converter 120 and a speaker 130, the digital-to-analog converter 120 is electrically connected to the multi-tone generator 110 and the speaker 130, the multi-tone generator 110 generates a digital signal according to information pre-written into a memory (not shown in the figure) of the apparatus, the digital-to-analog converter 120 performs digital-to-analog conversion on the digital signal, converts the digital signal into an analog signal, and then plays the analog signal outwards through the speaker 130 for the smart device that needs to be awakened to receive the analog signal. The multitone generator 110, the dac 120, the speaker 130 and the connection thereof are well known to those skilled in the art and will not be described herein.

To further explain the method in the present disclosure, an information transmission path between the transmitting-end smart device and the receiving-end smart device, and necessary hardware devices in the transmitting-end smart device and the receiving-end smart device, which are referred to in the present disclosure, are explained. Referring to fig. 2, the transmitting end device includes a multi-tone generator 110, a digital-to-analog converter 120 and a speaker 130, the digital-to-analog converter 120 is electrically connected to the multi-tone generator 110 and the speaker 130, the multi-tone generator 110 generates a digital signal according to information pre-written into a memory (not shown in the figure) of the device, the digital-to-analog converter 120 performs digital-to-analog conversion on the digital signal, converts the digital signal into an analog signal, and then plays the analog signal through the speaker 130 to the outside for the smart device to be woken up to receive the analog signal.

The receiving end device includes an audio receiver 140, an analog-to-digital converter 150 and a wake-up unit 160, wherein the analog-to-digital converter 150 is electrically connected to the audio receiver 140 and the wake-up unit 160, respectively. The audio receiver 140 receives a sound signal from an external environment and sends the sound signal to the analog-to-digital converter 150, the analog-to-digital converter 150 converts the sound signal from an analog signal to a digital signal and sends the converted data to the wakeup unit 170, and the wakeup unit 170 determines whether to wake up the preset function of the receiving-end intelligent device according to whether there is multi-frequency sound in the received digital signal.

Transmitting terminal equipment is before giving out the multifrequency, will generate the multifrequency, and the multifrequency is superimposed by the single-frequency sound of a plurality of frequency channels and is formed, uses the superposition of a plurality of single-frequency signal that have specific frequency to form the multifrequency in this disclosure, and the sound analysis mode after no matter be the sound synthesis mode or receiving the multifrequency is all fairly simple, can not occupy smart machine's processing resource in a large number. Meanwhile, in order to avoid the auditory discomfort brought to the user by single playing of the multi-frequency sound, when the multi-frequency sound is synthesized, the sound source can be used as a basis, and a plurality of single-frequency sounds with specific frequencies are added into the sound source, so that the use experience of the user is improved. The principle of synthesis of multi-tones will be explained below.

In synthesizing a multitone, a sampling interval is considered, which determines a frequency difference between single tones selected for synthesizing the multitone, which should be an integer multiple of the sampling interval, when synthesizing the multitone.

In one example, the sampling interval represents a frequency range

Wherein, F_sB is the number of points of the fourier transform for the sampling rate. For example, the sampling rate F_s16000Hz, the number of points of the Fourier transform is 256, and the frequency range represented by the sampling interval is

In order to ensure that the synthesized polyphones, after being received and identified by the smart device, correspond to as many frequency points after the fourier transform as possible, a multiple of 64.5Hz, such as 64.5Hz, 129Hz, 193.5Hz, is selected as the frequency of the single-tone to be used for synthesizing the polyphones. In this example, several single-frequency tones may be directly selected to be synthesized as the wake-up information, and the several single-frequency tones may be integer multiples of 64.5 Hz.

In addition to the above-described multitone using 64.5Hz as a base, a multitone using 0.25KHz as a base may be selected, as shown in fig. 3, which is a frequency distribution of multitone formed by 1KHz, 1.25KHz, and 1.5KHz as single tones.

In another example, music is used as the base frequency, and a single frequency tone with a specific frequency is added to the base frequency to generate the wake-up information. Since the wake-up information in this example takes music as fundamental frequency, multi-frequency sound is added to the music of the pleasant, which enhances the hearing experience of the user. In this example, as shown in fig. 4, a plurality of single tones are selected to synthesize multi-tones, and the multi-tones are synthesized into a fundamental frequency, wherein the frequencies of the plurality of single tones are, for example, 1KHz, 1.25KHz, 1.5KHz …, and the average value is an integer multiple of 0.25 KHz. The wake-up information may be expressed as:

y(t)＝Asin(2π×1kt)+Bsin(2π×1.25kt)+Csin(2π×1.5kt)+Dsin(2π×ωt)+...

wherein y (t) is wake-up information; t is a duration vector; A. b, C, D is the amplitude of the signal; ω is the angular frequency. The selection of ω may be set according to the effect of the music to be added, in this example, the fundamental frequency of the music may be 250Hz or an integral multiple of 250Hz, so that the smart device determines the wake-up information in the sound information after receiving the sound information.

Here, in the present example, in order to set a pleasant music, a single tone formed according to the above-described rule may be further superimposed. The numerical values shown in the present example are used for illustration only, and are not intended to limit the technical contents of the present disclosure.

To explain the wake-up method of the smart device in the present disclosure, first, an entity apparatus related to the smart device is explained. At present, most intelligent devices such as intelligent sound equipment and intelligent mobile phones are provided with a function of supporting voice awakening. The user sends out specific statement and awakens up smart machine, makes things convenient for daily use. However, statements used in the voice awakening process are complex, complex calculation needs to be performed when the intelligent device recognizes voice information, and the power consumption of the intelligent device is high due to the large calculation amount. For intelligent devices supporting voice wake-up function, sound wave collectors such as microphones are arranged on the intelligent devices. In order to realize the voice awakening function, the microphone is kept in a normally open state and is in a mobile phone sound wave state, and meanwhile, the intelligent equipment is further provided with a sound wave signal processing device for preprocessing or time domain and frequency domain transformation and the like after sound information is received.

The awakening method of the intelligent device can be applied to the intelligent device with the voice awakening function, the intelligent device can have the voice awakening function at the same time, the multi-tone awakening function can be provided, the awakening method can be executed without adding other hardware devices and extra power consumption, hardware cost for implementing the method is reduced, and the method is convenient to popularize.

For a receiving-end intelligent device having both a voice wake-up function and the multi-frequency wake-up function in the present disclosure, some functions of the intelligent device that need to be interacted with a user to be executed may be woken up using a voice wake-up method in a set manner, for example, a search function, a music play function, and the like may be woken up using the voice wake-up function.

For some functions on the intelligent device which can be executed without interaction with the user, the multi-tone awakening method in the disclosure can be used for awakening, for example, the ultrasonic function of a mobile phone, interconnection among intelligent household appliances and the like, so that occupation of processing resources of the intelligent device is reduced, awakening efficiency is improved, and energy consumption of the intelligent device is reduced.

The intelligent device has the advantages that the voice awakening function and the multi-frequency awakening function can be simultaneously operated on the intelligent device, the interaction effect between a user and the intelligent device can be enhanced, the use of the voice awakening function can be reduced to a certain extent, and therefore the energy consumption of the intelligent device is reduced.

According to an exemplary embodiment, as shown in fig. 5, a wake-up method of a smart device in the present embodiment, where the wake-up method is executed by the smart device, includes:

and S110, receiving the voice information.

In this step, receiving the sound information may be performed by a sound reception module on the smart device, which may be, for example, to a microphone provided on the smart device.

S120, judging whether the sound information contains multi-frequency sound, if so, executing a step S130;

if not, the process returns to step S110.

In this step, if the multitone detected in the received sound information by the smart device used as the receiving end indicates that the received sound information contains the wake-up information, the smart device needs to wake up the preset function of the smart device.

If the intelligent device used as the receiving end does not detect the multi-frequency sound in the received sound information, which indicates that the sound information is not the multi-frequency sound which is sent by the intelligent device used as the transmitting end and used as the awakening information, the currently received sound information can be ignored, and the sound information in the external environment is continuously received.

The smart device used as the receiving end may obtain the sound information in its surrounding environment every preset time interval, for example, receive the sound information in its surrounding environment every 20 ms. The preset time period can be set according to actual conditions, and the content of the disclosure is not limited substantially.

S130, awakening the preset function of the intelligent device.

The preset function in this embodiment may be, for example, a standby state wake-up function of the smart device used as the receiving end. The intelligent device is in a standby state before receiving the multi-frequency sound, and after the intelligent device receives the multi-frequency sound in the sound information, the standby state is awakened, and the intelligent device is converted into a use state from the standby state.

When the intelligent device in this embodiment is an air conditioner, the preset function may be a cooling or heating function of the air conditioner, and the air conditioner is always in a standby state until the multi-frequency sound is not received by the air conditioner. When the air conditioner receives multi-frequency tones in the sound information in the surrounding environment, the air conditioner changes from the standby state to the hot-cold state or the heating state.

The awakening method in the disclosure judges whether the sound information received by the intelligent device contains multi-frequency sound so as to determine whether to awaken the preset function of the intelligent device. Because this disclosure uses the frequency domain characteristic as the basis of judging, when guaranteeing to awaken up the accuracy, can also reduce the complexity in the sound information processing process, reduce the energy consumption of smart machine.

According to an exemplary embodiment, as shown in fig. 6, the wake-up method of the smart device in this embodiment is applied to the smart device used as a receiving end, and the smart device in this embodiment includes:

s210, receiving sound information.

This step is the same as the step S110 in the above embodiment, and is not described herein again.

S220, judging whether the sound information contains characteristic audio information according to the first preset information so as to determine whether the sound information contains multi-frequency sound.

If yes, go to step S230; if not, the process returns to step S210.

In step S210, the first preset information may be pre-stored in the memory of the smart device, and after the sound receiving module receives the sound information, the processing module of the smart device obtains the first preset information from the memory to determine whether the sound information includes the wakeup information. The first preset information includes a plurality of reference single-frequency tone features, and the reference single-frequency tone features may be, for example, frequency features of single-frequency tones.

After receiving the sound information, judging whether the sound information contains characteristic audio information or not, wherein the characteristic audio information comprises a plurality of single-frequency tones. The first preset information comprises a plurality of reference single-frequency tone characteristics, if the sound information comprises a plurality of single-frequency tones, and the plurality of single-frequency tones correspond to the plurality of reference single-frequency tone characteristics, the sound information comprises characteristic audio information; if the sound information does not have a plurality of single-frequency tones, or the single-frequency tones contained in the sound information do not correspond to the characteristics of the plurality of reference single-frequency tones, it is indicated that the sound information does not contain the characteristic sound information.

If the sound information does not contain the characteristic audio information, the sound information received by the intelligent equipment is not awakening information, the intelligent equipment does not awaken the preset function, and the current state is kept. If the sound information includes characteristic audio information, it indicates that the sound information may be a wake-up information, but not necessarily a wake-up information, and further determination is required (described in detail later).

And S230, determining that the sound information contains multi-frequency sound.

In this step, if the currently received sound information includes multi-frequency tones, it is indicated that the received sound information is used for waking up a preset function of the smart device.

And S240, determining whether the multi-frequency tone is awakening information according to the energy information of the single-frequency tones.

If yes, go to step S250; if not, the process returns to step S210.

The characteristic audio information in this embodiment is multi-frequency sound, and the multi-frequency sound is synthesized by a plurality of single-frequency sounds. When determining whether or not a multitone included in sound information is wake-up information, energy information of a plurality of single-tone is determined as a determination criterion. For example, energy information of each single tone may be considered separately to determine whether a multitone is a wake-up information; the sum of the energy information of the plurality of single tones may also be considered together to determine whether the characteristic audio information is a wake-up information.

And S250, awakening the preset function of the intelligent equipment.

After determining that the multi-frequency tone is the wake-up message in step S240, if it is determined that the received voice message is for waking up the preset function of the smart device, the preset function of the smart device is woken up. For example, the ultrasonic encoding function of the mobile phone is awakened, or the humidifying function of the humidifier is awakened.

According to an exemplary embodiment, as shown in fig. 7, the waking method of the smart device in this embodiment is further defined by step S240 in the foregoing embodiment, and includes:

and S310, performing framing processing on each single-frequency tone.

In this step, the processing module of the intelligent device performs framing processing on each single-frequency tone, wherein, in order to obtain a better framing effect, frequency domain analysis is conveniently performed on the single-frequency tones, and framing windowing processing can be performed on each single-frequency tone.

When performing the windowing process on the frame, x is processed_(n)Dividing according to the frame length L to obtain frame data x₁、x₂…x_kWhere L is typically an integer power of 2, e.g., 128, 256; k is the sequence number of the frame.

Then, a windowing operation is performed on each frame of data, x_wi＝window(x_i) I is 1, 2 … k, and windowed frame data x is obtained_w1、x_w2…x_wkWherein window represents a window function.

And S320, respectively determining the frame energy information of each frame data of each single frequency tone.

In this step, when determining the frame energy information of each frame of data, the method specifically includes:

firstly, frequency domain transformation is respectively carried out on each frame of data of each single-frequency tone, and frequency domain information of each frame of data of each single-frequency tone is determined.

After the single-frequency tones are subjected to framing processing, for each single-frequency tone, performing fourier transform on each frame of data after windowing, and completing frequency domain transform on each frame of data of each single-frequency tone so as to determine frequency domain information X1 and X2 … Xi of each frame of data of each single-frequency tone. Wherein Xk ═ FT (x)_wi)，i＝1，2…k。

After each single-frequency tone is subjected to fourier transform, the set of frequency domain information including each frame is obtained, that is, how many single-frequency tones are, how many sets of frequency domain information are obtained.

And then, respectively determining the frequency point corresponding to each single-frequency tone according to the frequency domain information of each frame of data of each single-frequency tone.

In the above description of multi-tone synthesis, the number of fourier transforms is mentioned, and the number of fourier transforms is a parameter during fourier transform, and those skilled in the art know how to implement frequency domain transform by using fourier transform, and will not be described herein again. Assuming that the number of points of the fourier transform is M, for each single tone, the frequency domain information Xi of each frame of data included in the single tone may be decomposed into M corresponding frequency points.

In one example, assuming that the frequency f of a single tone is 1000, the number of fourier transform points M is 128, and FS is 16000, the method is based on

It can be determined that b equals round (1000 equals 128/16000) equals 8

Where b represents the several points among the frequency points corresponding to the M of the frequency domain information Xi. When b is 8, the 8 th point in the M frequency points is the frequency point corresponding to the single frequency tone.

And then, respectively determining the frequency point energy information of each single frequency point.

In this step, in one example, assume X_i(8) Is 0.025+0.012i, according to the formula:

p＝mod{X_i(b) p ═ mod (0.025+0.012i) ═ 0.0277 can be determined.

The power, namely the energy information of the frequency point corresponding to each frame data of each single-frequency tone after the fourier transform is calculated, so that whether the characteristic audio information is the wake-up information or not is determined according to the frame energy information of the single-frequency tone in the subsequent steps.

And then, according to the point energy information of the frequency point of each single-frequency tone, determining the frequency band energy information of the frequency band where the frequency point of each single-frequency tone is located.

In this step, after the point energy information of the frequency point of the single frequency tone is determined in the above step, it is necessary to further determine the frequency band energy information where the frequency point of the single frequency tone is located, that is, the power of the frequency band corresponding to the frequency point.

And determining whether the frame energy information is greater than a preset energy threshold value according to the ratio of the point energy information of the frequency point to the frequency band energy information corresponding to the frequency point. That is, if the ratio of the point energy information of the frequency point to the frequency band energy information is greater than the preset energy threshold, it indicates that the frequency point passes, that is, the frequency point passes the judgment, and the subsequent steps can be continued to be judged.

When determining the frequency band energy information, the selection of the frequency band may be determined according to the actual situation. For example, if the multi-tone is subjected to framing processing and judgment, the frequency band range may be large. For another example, if each single tone of the multi-tones is used to perform framing processing and judgment, the frequency band range may be smaller, so as to further improve the judgment accuracy.

In one example, the framing processing is performed with the multi-tones as a whole in this example, and the judgment is performed for each frame data. Suppose K is the starting point of a frequency bin, N is the ending point of a frequency bin, and X_i(b) The frequency point corresponding to the b-th point in the N-K +1 points. Assuming that the frequency segment interval f where the frequency point b is located is 1000 to 1500, and the number of points of the fourier transform is 128, it can be determined according to the formula for determining the frequency point b in the above step, and the value range of b is 8-12.

The frequency band energy information in the frequency band may be determined according to the following equation:

the band energy information RMS in this example is then:

in another example, in this example, each of the multiple tones is frame-split processed and a determination is made for each frame of data for each single tone. For each single tone, the amplitude is different, so the preset energy threshold corresponding to each single tone is also different. If the frequency point corresponding to a single tone of the multi-tones is the 7 th point of the M frequency points, the 6 th to 8 th points may be selected as the frequency band corresponding to the frequency point when determining the frequency band corresponding to the frequency point. And determining frequency band energy information according to the formula, and further determining the relation between the frame energy information of the single-frequency tone and a preset energy threshold.

And S330, determining whether the multi-frequency tone is awakening information according to the frame energy information of each single-frequency tone.

And determining whether the characteristic audio information is awakening information according to the frame energy information.

According to an exemplary embodiment, as shown in fig. 8, the waking method of the smart device in this embodiment further defines step S330 in the foregoing embodiment, and the method in this embodiment further includes, on the basis of the foregoing embodiment:

s410, respectively judging whether the frame energy information of each single-frequency tone meets a preset condition;

if yes, go to step S420; if not, returning.

The preset condition is that a single frequency tone has continuous N frames of signals, and the frame energy information of each frame of data exceeds a preset energy threshold corresponding to the single frequency tone.

In this step, in a specific determination process, it is determined whether the frame energy information of each single-frequency tone satisfies a preset condition, and if the frame energy information of each single-frequency tone exceeds a preset energy threshold and exists in consecutive N frame signals, and the frame energy information of each single-frequency tone exceeds the preset energy threshold, each single-frequency tone satisfies the preset condition, and it is determined that the received sound information includes the wakeup information.

If the frame energy information of any one of the plurality of single tones does not exceed the preset energy threshold, it indicates that the frame energy information of each single tone does not satisfy the preset condition. Meanwhile, if the frame energy information of each single-frequency tone meeting the preset condition is not continuous N frames but is intermittent, or N-1 frames are continuous, and the N frame is not continuous with the previous N-1 frame, the multi-frequency tone does not meet the preset condition, and the received sound information does not contain awakening information.

And S420, if each single-frequency tone meets the preset condition, determining the multi-frequency tone as the awakening information.

If each single-frequency tone meets the preset condition in the judging process of the step, the multi-frequency tone contained in the sound information is described as the awakening information, and the preset function of the intelligent device can be awakened.

And if the sound information does not contain the awakening information, automatically ignoring the received sound information and not awakening the preset function.

According to an exemplary embodiment, the method in this embodiment is applied to a process of further synthesizing multiple tones synthesized by multiple single-tone tones with a sound source to form wake-up sound information, that is, signals sent to the smart device by other devices are music signals. As shown in fig. 9, the wake-up method in this embodiment further includes the following steps in addition to the method in the above embodiment:

and S510, receiving sound information.

S520, judging whether the sound information contains characteristic fundamental frequency information or not according to the second preset information;

if yes, go to step S530; if not, the process returns to step S510.

The second preset information comprises a reference fundamental frequency characteristic, and the characteristic fundamental frequency information corresponds to the reference fundamental frequency characteristic.

In this step, the second preset information may be pre-stored in the memory of the smart device, and after the sound receiving module receives the sound information, the processing module of the smart device obtains the second preset information from the memory to determine whether the sound information includes the wakeup information. The second preset information includes reference fundamental frequency information, which may be, for example, a music frequency characteristic.

After receiving the sound information, judging whether the sound information contains characteristic fundamental frequency information, if the sound information contains characteristic fundamental frequency information corresponding to the reference fundamental frequency characteristic, the sound information possibly comprises wake-up information, but further judgment is needed to determine whether the sound information containing the characteristic fundamental frequency information contains the wake-up information. If the sound information does not contain the characteristic fundamental frequency information, which indicates that the sound information cannot be used as the wake-up information, the sound information is ignored.

And S530, if the sound information contains the characteristic fundamental frequency information, awakening the preset function of the intelligent equipment according to the multi-frequency sound.

In the method in this embodiment, because the signal sent to the smart device by another device is a music signal, the method in this embodiment needs to determine, in addition to the characteristic audio information shown in the above other embodiments, whether a pitch of a fundamental frequency in the received sound signal is consistent with reference fundamental frequency information in the second configuration information, and if the sound information includes the characteristic fundamental frequency information, which indicates that the sound information may include wake-up information, further determination needs to be performed according to energy information of each single-frequency tone or according to overall energy information of multiple tones, to determine whether multiple tones included in the sound information are wake-up information, so as to determine whether to wake-up a preset function of the smart device.

According to an exemplary embodiment, the present embodiment is applied to the ultrasound system wake-up process of the smart device, that is, when the preset function is the ultrasound system of the smart device, the duration of the ultrasound encoding performed by the ultrasound system is determined according to the duration of the received characteristic audio information.

In one example, in an actual implementation process, the ultrasonic system is controlled to start ultrasonic coding from the moment when the characteristic audio information is received, and the ultrasonic system is controlled to stop ultrasonic coding from the moment when the characteristic audio information stops, so that the ultrasonic coding work of the ultrasonic system is synchronized according to the received awakening information. In order to avoid mutual interference between the multi-frequency sound as the wake-up information and the ultrasonic coded digital signal, when the wake-up information is set, the frequency band where the ultrasonic coded signal is located is avoided as much as possible.

In order to further explain the awakening method of the smart device in the present disclosure, the ultrasound system that receives the sound information to awaken the smart device is taken as an application scenario, and the awakening method in the present disclosure is explained in conjunction with a system block diagram.

As shown in fig. 10, the transmitting end 200 of the wake-up information includes an encoder 210, a combiner 220, and a digital-to-analog signal converter 230, which are connected in sequence, a wake-up information generator 240 electrically connected to the combiner 220, and an acoustic wave generator 250 electrically connected to the digital-to-analog signal converter 230. The encoder 210 is configured to start encoding the ultrasonic digital signal when receiving an instruction to send the wake-up message, and send the ultrasonic encoded digital signal to the combiner 220 after encoding. Meanwhile, the wakeup information generator 240 starts generating wakeup information upon receiving an instruction to issue wakeup information, and transmits the wakeup information to the combiner 220. The combiner 220 combines the ultrasound encoded digital signal and the wake-up information to generate the ultrasound encoded digital signal with the wake-up information. The digital-to-analog signal converter 230 receives the ultrasonic coded digital signal with the wake-up information, converts the ultrasonic coded digital signal into an analog signal, and sends the analog signal to the sound generator 250 for playing.

The smart device 300 includes a sonic receiver 310, and an ultrasonic signal analog-to-digital converter 320 and a wake-up information analog-to-digital converter 330 electrically connected to the sonic receiver 310, respectively. The smart device further comprises a wake-up unit 340, which is connected to the ultrasound signal analog-to-digital converter 320 and the wake-up information analog-to-digital converter 330, respectively. In addition, the smart device further includes a decoder 350, and the decoder 350 is electrically connected to the ultrasonic signal analog-to-digital converter 320.

After receiving the sound information, the sound wave receiver 310 sends the sound information to the ultrasonic signal analog-to-digital converter 320 and the wakeup information analog-to-digital converter 330, the wakeup information analog-to-digital converter 330 performs analog-to-digital conversion on the sound information, if the sound information includes wakeup information, the wakeup unit 340 sends a wakeup instruction to the ultrasonic signal analog-to-digital converter 320, the ultrasonic signal analog-to-digital converter 320 is awakened, the ultrasonic signal analog-to-digital converter 320 performs analog-to-digital conversion on the ultrasonic signal in the received sound information, sends the ultrasonic signal in a digital signal state to the decoder 350, and stores the information or the instruction decoded by the decoder 350.

According to an exemplary embodiment, as shown in fig. 11, a detailed description is given below of a specific implementation procedure of the wake-up method of the smart device in the present disclosure. The wake-up method in this embodiment includes:

s610, receiving sound information;

s620, identifying characteristic audio information in the sound information;

s630, performing framing processing on a plurality of single-frequency tones contained in the characteristic audio information;

s640, respectively determining frame energy information of each frame of each single tone;

s650, judging whether the current frame energy information of each single-frequency tone is larger than a preset energy threshold corresponding to the single-frequency tone;

if yes, go to step S660, otherwise, go back to step S630;

s660, adding 1 to multi-tone frame data meeting a preset energy threshold;

s670, judging whether the multi-tone frame data meeting the preset energy threshold reach N frames or not;

if yes, go to step S680; if not, the process returns to step S630.

And S680, awakening a preset function.

Steps S650 to S670 are equivalent to respectively determining whether the frame energy information of each single tone satisfies a preset condition, where the preset condition is that the single tone has N consecutive frames, and the frame energy information of each frame of data exceeds the preset energy threshold corresponding to the single tone.

Here, it should be noted that, because the amplitudes of the single tones used for synthesizing the multi-tones are different, the preset energy thresholds corresponding to the single tones are also different, and when determining whether each single tone of the multi-tones satisfies the preset condition, the different preset energy thresholds should be used as the determination criteria, so as to further improve the determination accuracy.

In the embodiment, after the sound information is received, when whether the sound information contains multi-frequency sound, that is, whether the sound information contains the awakening information is determined, the energy information and the duration of the multi-frequency sound are considered, so that the accuracy of judging the awakening information in the sound information is improved, and the condition of false triggering is avoided.

Of course, it is understood that for some functions to be wakened which are not too important, it may not be necessary to consider both the energy information and the duration, but only a single factor.

In one example, as shown in fig. 12, the preset function of the smart device is the ultrasound system function of the smart device, i.e. when multi-tones are received, the ultrasound system of the smart device is woken up. In addition, in this example, the multitone is a synthesis of a plurality of simple single-frequency tones, and does not include other music information, and when the preset function is awakened, only the duration of receiving the multitone in the sound information is considered in this example, and the method in this example includes:

and S710, receiving the voice information.

S720, judging whether the sound information contains multi-frequency sound;

if yes, go to step S730; if not, the process returns to step S710.

And S730, waking up the ultrasonic system.

And S740, determining the time length of the received multi-frequency sound.

And S750, determining the time length of the ultrasonic coding of the ultrasonic system according to the time length of the received multi-frequency sound.

In another example, as shown in fig. 13, in this example, the preset function of the smart device is still the ultrasound system function of the smart device. In this example, the audio as the wake-up information includes both multi-frequency tones and fundamental frequency information, i.e., music information. And in this example both the duration and energy information of the multitone are considered. The method in this example includes:

and S810, receiving the voice information.

S820, judging whether the sound information contains fundamental frequency information;

if yes, go to step S830, otherwise, go back to step S810.

S830, judging whether the sound information contains multi-frequency sound;

if yes, go to step S840, otherwise, go back to step S810.

And S840, judging whether the energy information and the duration of the multi-frequency sound meet preset conditions.

If yes, go to step S850, otherwise return to step S810.

And S850, waking up the ultrasonic system.

And S860, determining the time length of the received multi-frequency tone.

And S870, determining the time length of the ultrasonic system for ultrasonic coding.

According to an exemplary implementation, as shown in fig. 14, the wake-up method of the smart device in this embodiment may also be implemented by using the smart system as shown in fig. 10, and the wake-up method in this embodiment is applied to the receiving-end smart device. The method in the embodiment comprises the following steps:

s910, receiving the voice information.

S920, judging whether the sound information contains multi-frequency sound;

if yes, go to step S930; if not, returning to step S910.

S930, framing the multi-tone.

And S940, determining frame energy information of each frame of data of the multi-frequency sound.

S950, judging whether the frame energy information of continuous N frame data exceeds a preset energy threshold value;

if yes, go to step S960; if not, the process returns to step S930.

And S960, determining the multi-frequency tone as the awakening information.

S970, awakening the preset function of the intelligent device.

In this embodiment, when determining whether the multi-frequency is the wake-up information, the multi-frequency is taken as a whole, and is subjected to framing processing, so as to determine, according to each frame of data of the multi-frequency, whether frame energy information of consecutive N frames of data exceeds a preset energy threshold, that is, the duration and the energy information of the multi-frequency are considered at the same time, and if the consecutive N frames of data of the multi-frequency exceeds the preset energy threshold, it is determined that the multi-frequency is the wake-up information, and a preset function of the intelligent device is woken up.

With multifrequency as whole in this embodiment carry out the processing of framing, the processing procedure is simpler, high-efficient, has promoted the treatment effeciency of multifrequency.

The present disclosure also provides a wake-up apparatus for an intelligent device, where the wake-up apparatus is used to implement the wake-up method for the intelligent device recorded in the above embodiments.

According to an exemplary embodiment, as shown in fig. 15, the wake-up apparatus is applied to a smart device used as a receiving end. The wake-up apparatus in this embodiment includes a radio receiving module 410 and a processing module 420 electrically connected to each other. The apparatus in this embodiment is configured to implement the wake-up method applied to the smart device at the receiving end shown in the foregoing embodiment.

Fig. 16 is a block diagram of an intelligent device. The present disclosure also provides an intelligent device comprising a processor; a memory for storing executable instructions of the processor. Wherein the processor is configured to perform the method described above. The device 500 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, fitness device, personal digital assistant, or the like. The smart device may also be a light sensitive element, such as a light sensor.

Device 500 may include one or more of the following components: a processing component 502, a memory 504, a power component 506, a multimedia component 508, an audio component 510, an input/output (I/O) interface 512, a sensor component 514, and a communication component 516.

The processing component 502 generally controls overall operation of the device 500, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 502 may include one or more processors 520 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 502 can include one or more modules that facilitate interaction between the processing component 502 and other components. For example, the processing component 502 can include a multimedia module to facilitate interaction between the multimedia component 508 and the processing component 502.

The memory 504 is configured to store various types of data to support operation at the device 500. Examples of such data include instructions for any application or method operating on device 500, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 504 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

Power component 506 provides power to the various components of device 500. Power components 506 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for device 500.

The multimedia component 508 includes a screen that provides an output interface between the device 500 and the user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 508 includes a front facing camera and/or a rear facing camera. The front-facing camera and/or the rear-facing camera may receive external multimedia data when the device 500 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 510 is configured to output and/or input audio signals. For example, the audio component 510 includes a Microphone (MIC) configured to receive external audio signals when the device 500 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 504 or transmitted via the communication component 516. In some embodiments, audio component 510 further includes a speaker for outputting audio signals.

The I/O interface 512 provides an interface between the processing component 502 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 514 includes one or more sensors for providing various aspects of status assessment for the device 500. For example, the sensor assembly 514 may detect an open/closed state of the device 500, the relative positioning of the components, such as a display and keypad of the device 500, the sensor assembly 514 may also detect a change in the position of the device 500 or a component of the device 500, the presence or absence of user contact with the device 500, orientation or acceleration/deceleration of the device 500, and a change in the temperature of the device 500. The sensor assembly 514 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 514 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 514 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 516 is configured to facilitate communications between the device 500 and other devices in a wired or wireless manner. The device 500 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 516 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 516 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 500 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

A non-transitory computer readable storage medium, such as the memory 504 including instructions executable by the processor 520 of the device 500 to perform the method, is provided in another exemplary embodiment of the present disclosure. For example, the computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like. The instructions in the storage medium, when executed by a processor of the smart device, enable the smart device to perform the above-described method.

Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.

It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.

Claims

1. A wake-up method of an intelligent device is applied to a receiving end intelligent device, and is characterized in that the wake-up method comprises the following steps:

receiving sound information;

judging whether the sound information contains multi-frequency sound;

and if the sound information contains the multi-frequency sound, awakening the preset function of the intelligent equipment according to the multi-frequency sound.

2. The method for waking up a smart device according to claim 1, wherein the waking up the preset function of the smart device according to the multi-tone comprises:

framing the multi-frequency sound;

determining frame energy information for each frame of data of the multi-tone;

3. The method of claim 2, wherein the determining whether the multi-frequency tone is the wake-up information according to the frame energy information of each frame of data of the multi-frequency tone comprises:

and if so, determining the multi-frequency tone as the awakening information.

4. The method of claim 1, wherein the determining whether the sound information includes multi-frequency sound comprises:

5. The method for waking up a smart device according to claim 4, wherein the waking up the preset function of the smart device according to the multi-tone comprises:

6. The method of claim 5, wherein the determining whether the multi-frequency tone is the wake-up information according to the energy information of the single-frequency tones comprises:

respectively carrying out frame processing on each single-frequency tone;

7. The method of claim 6, wherein the determining whether the multi-frequency tone is a wake-up message according to the frame energy information of each single-frequency tone comprises:

8. The smart device wake-up method according to claim 1, further comprising:

9. The smart device wake-up method according to claim 1 or 8, wherein when the preset function is an ultrasound system function of the smart device, the wake-up method comprises:

10. The method for waking up a smart device according to claim 9, wherein the determining a duration of ultrasound encoding by an ultrasound system according to the received duration of the multi-frequency tones comprises:

11. The utility model provides a wake-up device of smart machine, is applied to receiving end smart machine, its characterized in that, wake-up device includes:

the radio module is used for receiving sound information;

12. The wake-up apparatus of a smart device according to claim 11, wherein the processing module is specifically configured to:

framing the multi-frequency sound;

determining frame energy information for each frame of data of the multi-tone;

13. The wake-up apparatus of a smart device according to claim 12, wherein the processing module is specifically configured to:

and if so, determining the multi-frequency tone as the awakening information.

14. The wake-up apparatus of a smart device according to claim 11, wherein the processing module is specifically configured to:

15. The wake-up apparatus of a smart device according to claim 14, wherein the processing module is specifically configured to:

16. The wake-up apparatus of a smart device according to claim 15, wherein the processing module is specifically configured to:

respectively carrying out frame processing on each single-frequency tone;

17. The wake-up unit of a smart device of claim 16, wherein the processing module has a function for:

18. The wake-up apparatus of a smart device according to claim 11, wherein the processing module is specifically configured to:

19. The wake-up apparatus of an intelligent device according to claim 11 or 18, wherein when the preset function is an ultrasound system function of the intelligent device, the processing module is specifically configured to:

20. The wake-up apparatus of a smart device according to claim 19, wherein the processing module is specifically configured to:

21. A smart device, comprising:

a processor;

a memory for storing executable instructions of the processor;

wherein the processor is configured to perform the wake-up method of the smart device of any one of claims 1 to 10.

22. A non-transitory computer readable storage medium, wherein instructions in the storage medium, when executed by a processor of a smart device, enable the smart device to perform the wake-up method of the smart device according to any one of claims 1 to 10.